Machine Learning of Thermodynamic Observables in the Presence of Mode
Collapse

Machine Learning of Thermodynamic Observables in the Presence of Mode Collapse

22 November 2021

Christopher J. Anders

Shinichi Nakajima

Papers citing "Machine Learning of Thermodynamic Observables in the Presence of Mode Collapse"

9 / 9 papers shown

Title
Simulating the Hubbard Model with Equivariant Normalizing Flows Dominic Schuh Janik Kreit Evan Berkowitz L. Funcke Thomas Luu K. Nicoli Marcel Rodekamp 47 3 0 13 Jan 2025
AdvNF: Reducing Mode Collapse in Conditional Normalising Flows using Adversarial Learning V. Kanaujia Mathias S. Scheurer Vipul Arora GAN DRL 32 2 0 29 Jan 2024
Applications of flow models to the generation of correlated lattice QCD ensembles Ryan Abbott Aleksandar Botev D. Boyda D. Hackett G. Kanwar S. Racanière Danilo Jimenez Rezende Fernando Romero-López P. Shanahan Julian M. Urban AI4CE 198 11 0 19 Jan 2024
Multi-Lattice Sampling of Quantum Field Theories via Neural Operator-based Flows Bálint Máté Franccois Fleuret AI4CE 34 0 0 01 Jan 2024
Detecting and Mitigating Mode-Collapse for Flow-based Sampling of Lattice Field Theories K. Nicoli Christopher J. Anders T. Hartung K. Jansen Pan Kessel Shinichi Nakajima 29 22 0 27 Feb 2023
On Sampling with Approximate Transport Maps Louis Grenioux Alain Durmus Eric Moulines Marylou Gabrié OT 27 15 0 09 Feb 2023
Gradients should stay on Path: Better Estimators of the Reverse- and Forward KL Divergence for Normalizing Flows Lorenz Vaitl K. Nicoli Shinichi Nakajima Pan Kessel 61 24 0 17 Jul 2022
Learning Lattice Quantum Field Theories with Equivariant Continuous Flows Mathis Gerdes P. D. Haan Corrado Rainone Roberto Bondesan Miranda C. N. Cheng AI4CE 24 40 0 01 Jul 2022
Flow-based density of states for complex actions J. Pawlowski Julian M. Urban 16 10 0 02 Mar 2022